Video content posting and chapter recognition

A method of recognizing a chapter, comprising:

• determining text recognition information of an image frame of video content, the text recognition information indicating a first group of text boxes in the image frame;
• fusing, in response to the first group of text boxes comprising a plurality of positionally associated text boxes, the plurality of associated text boxes in the first group of text boxes to determine a second group of text boxes;
• determining, based on trajectory information of the second group of text boxes across a plurality of image frames, a chapter text box indicating chapter information from the second group of text boxes;
• and
• determining, based on text content in the chapter text box, the chapter information of the video content, the chapter information indicating a plurality of chapter titles of the video content.

A computing device, comprising:

• at least one processor;
• and
• at least one memory, the at least one memory being coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, causing the computing device to perform acts comprising:
• presenting a posting interface of video content;
• presenting, in response to obtaining first chapter information recognized based on the video content, guidance information in the posting interface;
• presenting, in response to triggering of the guidance information, a chapter setting interface of the video content, the chapter setting interface presenting a first group of chapter titles determined based on the first chapter information;
• and
• determining, via the chapter setting interface, second chapter information of the video content to post the video content, the second chapter information at least indicating a second group of chapter titles of the video content.